Distributed word representations have become an essential foundation for biomedical natural language processing (BioNLP), text mining and information retrieval. Word embeddings are traditionally computed at the word level from a large corpus of unlabeled text, ignoring the information present in the internal structure of words or any information available in domain specific structured resources such as ontologies. However, such information holds potentials for greatly improving the quality of the word representation, as suggested in some recent studies in the general domain. Here we present BioWordVec: an open set of biomedical word vectors/embeddings that combines subword information from unlabeled biomedical text with a widely-used biomedical controlled vocabulary called Medical Subject Headings (MeSH). We assess both the validity and utility of our generated word embeddings over multiple NLP tasks in the biomedical domain. Our benchmarking results demonstrate that our word embeddings can result in significantly improved performance over the previous state of the art in those challenging tasks.

Supplementary data are available at Bioinformatics online.

Motivation: Detecting drug-drug interaction (DDI) has become a vital part of public health safety. Therefore, using text mining techniques to extract DDIs from biomedical literature has received great attentions. However, this research is still at an early stage and its performance has much room to improve.Results: In this article, we present a syntax convolutional neural network (SCNN) based DDI extraction method. In this method, a novel word embedding, syntax word embedding, is proposed to employ the syntactic information of a sentence. Then the position and part of speech features are introduced to extend the embedding of each word. Later, auto-encoder is introduced to encode the traditional bag-of-words feature (sparse 0–1 vector) as the dense real value vector. Finally, a combination of embedding-based convolutional features and traditional features are fed to the softmax classifier to extract DDIs from biomedical literature. Experimental results on the DDIExtraction 2013 corpus show that SCNN obtains a better performance (an F-score of 0.686) than other state-of-the-art methods.Availability and Implementation: The source code is available for academic use at http://202.118.75.18:8080/DDI/SCNN-DDI.zip.Contact: yangzh@dlut.edu.cnSupplementary information: Supplementary data are available at Bioinformatics online.

MotivationAdverse events resulting from drug-drug interactions (DDI) pose a serious health issue. The ability to automatically extract DDIs described in the biomedical literature could further efforts for ongoing pharmacovigilance. Most of neural networks-based methods typically focus on sentence sequence to identify these DDIs, however the shortest dependency path (SDP) between the two entities contains valuable syntactic and semantic information. Effectively exploiting such information may improve DDI extraction.ResultsIn this article, we present a hierarchical recurrent neural networks (RNNs)-based method to integrate the SDP and sentence sequence for DDI extraction task. Firstly, the sentence sequence is divided into three subsequences. Then, the bottom RNNs model is employed to learn the feature representation of the subsequences and SDP, and the top RNNs model is employed to learn the feature representation of both sentence sequence and SDP. Furthermore, we introduce the embedding attention mechanism to identify and enhance keywords for the DDI extraction task. We evaluate our approach using the DDI extraction 2013 corpus. Our method is competitive or superior in performance as compared with other state-of-the-art methods. Experimental results show that the sentence sequence and SDP are complementary to each other. Integrating the sentence sequence with SDP can effectively improve the DDI extraction performance.Availability and implementationThe experimental data is available at https://github.com/zhangyijia1979/hierarchical-RNNs-model-for-DDI-extraction.Supplementary information Supplementary data are available at Bioinformatics online.

Static cold storage (SCS) and hypothermic machine perfusion (HMP) are two primary options for renal allograft preservation. Compared with SCS, HMP decreased the incidence of delayed graft function (DGF) and protected graft function. However, more evidence is still needed to prove the advantages of the HMP. In this study, the outcomes of kidney grafts from the two preservation methods were compared by conducting a systematic review and meta-analysis. Randomized controlled trials (RCTs) comparing the effect of hypothermic machine perfusion and static cold storage in deceased donor kidney transplantation were identified through searches of the MEDLINE, EMBASE, and Cochrane databases between January 1, 1980 and December 30, 2017. The primary endpoints were delayed graft function and graft survival. Secondary endpoints included primary non-function (PNF), graft renal function, duration of DGF, acute rejection, postoperative hospital stay and patient survival. Summary effects were calculated as risk ratio (RR) with 95% confidence interval (CI) or mean difference (MD) with 95% confidence intervals (CI). A total of 13 RCTs were included, including 2048 kidney transplant recipients. The results indicated that compared with SCS, HMP decreased the incidence of DGF (RR 0.78, 95% CI 0.69-0.87, P < 0.0001), and improved the graft survival at 3 years (RR 1.06, 95% CI 1.02-1.11, P = 0.009). There was no significant difference in other endpoints. HMP might be a more desirable method of preservation for kidney grafts. The long-term outcomes of kidney allografts stored by hypothermic machine perfusion still need to be further investigated.